Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3502 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1170. Min Range: -1.1170

Max Act: 1.1062. Min Act: -0.0000

Data Index: 753572 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 1.1170. Min Range: -1.1170

Max Act: 1.1055. Min Act: -0.0000

Data Index: 159070 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 1.1170. Min Range: -1.1170

Max Act: 1.1170. Min Act: -0.0000

Data Index: 703670 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 1.1170. Min Range: -1.1170

Max Act: 1.0871. Min Act: -0.0000

Data Index: 941714 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 1.1170. Min Range: -1.1170

Max Act: 1.0326. Min Act: -0.0000

Data Index: 1370929 (Python Code)

Max Activating Token Index: 255

Text #5

Max Range: 1.1170. Min Range: -1.1170

Max Act: 1.0438. Min Act: -0.0000

Data Index: 471726 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.9707. Min Act: -0.0000

Data Index: 424141 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.9730. Min Act: -0.0000

Data Index: 535799 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.9267. Min Act: -0.0000

Data Index: 1089187 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.9559. Min Act: -0.0000

Data Index: 741446 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.9130. Min Act: -0.0000

Data Index: 1015188 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.7708. Min Act: -0.0000

Data Index: 647979 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.8657. Min Act: -0.0000

Data Index: 131616 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.8789. Min Act: -0.0000

Data Index: 739584 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.9093. Min Act: -0.0000

Data Index: 129793 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.8508. Min Act: -0.0000

Data Index: 714188 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.8505. Min Act: -0.0000

Data Index: 1053302 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.8730. Min Act: -0.0000

Data Index: 718776 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.8373. Min Act: -0.0000

Data Index: 125710 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.8117. Min Act: -0.0000

Data Index: 894019 (C4 (Web Text))

Max Activating Token Index: 357